OpenAI API Docs · Oct 21, 2026 · 2:21 AM

OpenAI's API can now keep prompt caches for 12 hours, aimed at agents that reuse context all day

Since Oct 20, GPT-5.6 and later models in the Responses API accept prompt_cache_options.ttl: "12h" (or a per-breakpoint ttl), with 12-hour cache writes billed at 2.5x input versus 1.25x for the default 30 minutes and reads unchanged (changelog). OpenAI's Tibo (@thsottiaux) added that caches for logged-in Codex and Work users will be kept permanently, so resuming an old conversation hits the cache (PANews).

Read at developers.openai.com

Codex

AI coding agent for features, refactors, reviews, and releases

More news

View all

Copilot CLI 1.0.100 lets sandboxed commands reach localhost and private networks by default

Now on npm latest , the release flips the command sandbox to allow local network access, so agent run commands can hit local databases and admin pages unless you lock it down, and adds trust folder for one off p runs plus a per session /sandbox toggle. It also stops sessions stalling when an MCP server hangs while loading tools (AI Dev Pulse)…

GitHub (github/copilot-cli) 8 minutes ago

Ornith-1.5-122B open-weights MoE coding model fits on a single 80GB GPU, MIT-licensed

Released Oct 20 with FP8, NVFP4, GGUF, and MLX variants, the reasoning model has a 262K context and serves via vLLM or SGLang with tool calling, and Ornith reports 0.845 on SWE bench Verified and 0.813 on Terminal Bench 2.1 (its own numbers, per HuggingNews). Community quants from AtomicChat bring it down to about 35GB for 64GB Macs…

Hugging Face (ornith-ai) 2 hours ago

Anthropic is reportedly testing a model that infers what you meant from incomplete coding instructions

Per The Information, a tester said the unreleased model spotted broader related problems when asked for a simple bug fix, but it's unclear whether it can tell an incomplete request from work you deliberately left out. That gap matters: the Overeager Coding Agents study found Claude Code, Codex CLI, and Gemini CLI took out of scope actions in 5.4% to 27.7% of runs, versus 0.2% to 4.5% for ask first OpenHands…

TechGig (via The Information) 3 hours ago

Cursor's pstack adds a skill that has your agent formally verify the riskiest invariant in your repo

Calling /create formal verification skill makes the agent pick a high stakes property (races, retries, parsers, unsafe code), choose a tool such as TLA+, CBMC, or Kani, show the check failing on a deliberately broken variant, then leave a project local skill so the next agent can rerun it with one command. pstack also ships into Claude Code's plugin marketplace from the same repo, and Cursor's own eval behind the skill is small (one run per repo on six open source projects)…

GitHub (cursor/plugins) 4 hours ago

OpenAI's MultiLangBench has models build SQLite from scratch in 20 languages, COBOL included

The open eval (GitHub) checks a from scratch SQLite 3.40.1 engine against 272 tests adapted from SQLite's own suite and scores pass rate alongside API cost; OpenAI says GPT 6 Astra averages 87.4% (COBOL hardest at 72.1%) vs 26.8% for GPT 5.6 Sol, while cheaper GPT 6 Luna hits 40.3% at about 78% lower cost. A separate COBOL migration eval has GPT 6.1 Sol at 97.9% on high reasoning, though all figures are OpenAI's own runs…

OpenAI 5 hours ago

Spotted something we missed? Start a thread.